Differential Diagnosis of Infectious Versus Autoimmune Encephalitis Using Artificial Intelligence-Based Modeling
David Petrosian1, Nataša Giedraitienė2, Vera Taluntienė2
1Faculty of Medicine, Vilnius University, Vilnius 03101, Lithuania.
Journal of Clinical Medicine
|November 27, 2025
Summary
This study developed an artificial intelligence model to differentiate autoimmune encephalitis from infectious encephalitis. The model accurately distinguishes between these conditions, aiding in faster diagnosis and improved patient outcomes.
Area of Science:
- Neuroscience
- Immunology
- Artificial Intelligence
Background:
- Encephalitis is a critical central nervous system inflammatory disorder requiring prompt diagnosis for favorable outcomes.
- Distinguishing autoimmune from infectious encephalitis is challenging but crucial for effective treatment.
- Autoimmune encephalitis encompasses diverse phenotypes and serostatuses, complicating differential diagnosis.
Purpose of the Study:
- To develop and validate an artificial intelligence (AI)-based model for differentiating autoimmune encephalitis from infectious encephalitis.
- To encompass a wide range of autoimmune encephalitis presentations, including paraneoplastic syndromes and seronegative cases.
- To enhance diagnostic accuracy and reduce uncertainty in clinical decision-making for encephalitis etiology.
Main Methods:
- Retrospective analysis of 233 patients with autoimmune or infectious encephalitis (2016-2024).
- Application of supervised machine learning techniques, including Random Forest, for model training.
- Utilized Shapley Additive Explanations (SHAP) for model interpretability.
Main Results:
- The Random Forest model achieved high performance in differentiating encephalitis etiology, with an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.966.
- Laboratory, electroencephalography, and clinical data were identified as the most significant predictors for classification.
- Imaging data showed a lesser contribution to the model's classification accuracy.
Conclusions:
- An AI model was successfully developed to distinguish infectious encephalitis from both seropositive and seronegative autoimmune encephalitis.
- The model holds potential to support clinical decision-making, particularly in cases where antibodies are not detected, preventing misdiagnosis.
- This AI tool can reduce diagnostic uncertainty, leading to more timely and appropriate patient management.
Keywords:
artificial intelligenceautoimmune encephalitisinfectious encephalitismachine learningparaneoplastic neurologic syndromesMore Related Videos
Related Concept Videos
01:19Encephalitis l: Introduction
Encephalitis is inflammation of the brain parenchyma, most often due to infections or autoimmune processes. It presents with neuropsychiatric features such as fever, altered mental status, behavioral changes, cognitive dysfunction, seizures, focal deficits, and sometimes autonomic instability. In some cases, the meninges are also involved, resulting in meningoencephalitis.Infectious CausesInfectious encephalitis is most commonly viral but can also result from bacterial, fungal, or parasitic...
01:26Encephalitis ll: Pathophysiology
Encephalitis is inflammation of the brain parenchyma caused by direct viral invasion or immune-mediated mechanisms triggered by infections or tumors. Both processes lead to neuronal injury, disrupted neurotransmission, and diverse neurological symptoms, often with overlapping clinical and pathological features.Autoimmune EncephalitisIn autoimmune encephalitis, antibodies target neuronal antigens on cell surfaces, synapses, or within neurons. A key example is anti-NMDAR encephalitis, which can...